Search

Fast and accurate diagnosis is essential for the efficient and effective control of the COVID-19 pandemic that is currently disrupting the whole world. Despite the prevalence of the COVID-19 outbreak, relatively few diagnostic images are openly available to develop automatic diagnosis algorithms. Traditional deep learning methods often struggle when data is highly unbalanced with many cases in one class and only a few cases in another; new methods must be developed to overcome this challenge. We propose a novel activation function based on the generalized extreme value (GEV) distribution from extreme value theory, which improves performance over the traditional sigmoid activation function when one class significantly outweighs the other. We demonstrate the proposed activation function on a publicly available dataset and externally validate on a dataset consisting of 1,909 healthy chest X-rays and 84 COVID-19 X-rays. The proposed method achieves an improved area under the receiver operating characteristic (DeLong's p-value < 0.05) compared to the sigmoid activation. Our method is also demonstrated on a dataset of healthy and pneumonia vs. COVID-19 X-rays and a set of computerized tomography images, achieving improved sensitivity. The proposed GEV activation function significantly improves upon the previously used sigmoid activation for binary classification. This new paradigm is expected to play a significant role in the fight against COVID-19 and other diseases, with relatively few training cases available.

Segmentation is a fundamental task in biomedical image analysis. Unlike the existing region-based dense pixel classification methods or boundary-based polygon regression methods, we build a novel graph neural network (GNN) based deep learning framework with multiple graph reasoning modules to explicitly leverage both region and boundary features in an end-to-end manner. The mechanism extracts discriminative region and boundary features, referred to as initialized region and boundary node embeddings, using a proposed Attention Enhancement Module (AEM). The weighted links between cross-domain nodes (region and boundary feature domains) in each graph are defined in a data-dependent way, which retains both global and local cross-node relationships. The iterative message aggregation and node update mechanism can enhance the interaction between each graph reasoning module’s global semantic information and local spatial characteristics. Our model, in particular, is capable of concurrently addressing region and boundary feature reasoning and aggregation at several different feature levels due to the proposed multi-level feature node embeddings in different parallel graph reasoning modules. Experiments on two types of challenging datasets demonstrate that our method outperforms state-of-the-art approaches for segmentation of polyps in colonoscopy images and of the optic disc and optic cup in colour fundus images. The trained models will be made available at: https://github.com/smallmax00/Graph_Region_Boudnary.

Echocardiography is an essential diagnostic method to assess cardiac functions. However, manually labelling the left ventricle region on echocardiography images is time-consuming and subject to observer bias. Therefore, it is vital to develop a high-performance and efficient automatic assessment tool. Inspired by the success of the transformer structure in vision tasks, we develop a lightweight model named ‘TransBridge’ for segmentation tasks. This hybrid framework combines a convolutional neural network (CNN) encoder-decoder structure and a transformer structure. The transformer layers bridge the CNN encoder and decoder to fuse the multi-level features extracted by the CNN encoder, to build global and inter-level dependencies. A new patch embedding layer has been implemented using the dense patch division method and shuffled group convolution to reduce the excessive parameter number in the embedding layer and the size of the token sequence. The model is evaluated on the EchoNet-Dynamic dataset for the left ventricle segmentation task. The experimental results show that the total number of parameters is reduced by 78.7% compared to CoTr [22] and the Dice coefficient reaches 91.4%, proving the structure’s effectiveness.

Affine registration has recently been formulated using deep learning frameworks to establish spatial correspondences between different images. In this work, we propose a new unsupervised model that investigates two new strategies to tackle fundamental problems related to affine registration. More specifically, the new model 1) has the advantage to explicitly learn specific geometric transformation parameters (e.g. translations, rotation, scaling and shearing); and 2) can effectively understand the context between the images via cross-stitch units allowing feature exchange. The proposed model is evaluated on two two-dimensional X-ray datasets and a three-dimensional CT dataset. Our experimental results show that our model not only outperforms state-of-art approaches and also can predict specific transformation parameters. Our core source code is made available online\(^{1}\)(\(^{1}\)https://github.com/xuuuuuuchen/PASTA).

Accurate segmentation of anatomic structure is an essential task for biomedical image analysis. Recent popular object contours regression based segmentation methods have increasingly attained researchers’ attentions. They made a new starting point to tackle segmentation tasks instead of commonly used dense pixels classification methods. However, because of the nature of CNN based network (lack of spatial information) and the difficulty of this methodology itself (need of more spatial information), these methods needed extra process to maintain more spatial features, which may cause longer inference time or tedious design and inference process. To address the issue, this paper proposes a simple, intuitive deep learning based contour regression model. We develop a novel multi-level, multi-stage aggregated network to regress the coordinates of the contour of instances directly in an end-to-end manner. The proposed network seamlessly links convolution neural network (CNN) with Attention Refinement module (AR) and Graph Convolution Network (GCN). By hierarchically and iteratively combining features over different layers of the CNN, the proposed model obtains sufficient low-level features and high-level semantic information from the input image. Besides, our model pays distinct attention to the objects’ contours with the help of AR and GCN. Primarily, thanks to the proposed aggregated GCN and vertices sampling method, our model benefits from direct feature learning of the objects’ contour locations from sparse to dense and the spatial information propagation across the whole input image. Experiments on the segmentation of fetal head (FH) in ultrasound images and of the optic disc (OD) and optic cup (OC) in color fundus images demonstrate that our method outperforms state-of-the-art methods in terms of effectiveness and efficiency.

This paper proposes a straightforward, intuitive deep learning approach for (biomedical) image segmentation tasks. Different from the existing dense pixel classification methods, we develop a novel multi-level aggregation network to directly regress the coordinates of the boundary of instances in an end-to-end manner. The network seamlessly combines standard convolution neural network (CNN) with Attention Refinement Module (ARM) and Graph Convolution Network (GCN). By iteratively and hierarchically fusing the features across different layers of the CNN, our approach gains sufficient semantic information from the input image and pays special attention to the local boundaries with the help of ARM and GCN. In particular, thanks to the proposed aggregation GCN, our network benefits from direct feature learning of the instances’ boundary locations and the spatial information propagation across the image. Experiments on several challenging datasets demonstrate that our method achieves comparable results with state-of-the-art approaches but requires less inference time on the segmentation of fetal head in ultrasound images and of optic disc and optic cup in color fundus images.